·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
America needs to stop getting shocked by Chinese AI2h◆Advancing next-gen AI with materials science innovation2h◆Gritt exits stealth with $34 million for robots to build solar plants—then, everything else3h◆Capacity and Redundancy Trade-offs in Multi-Task Learning9h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation9h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making9h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection9h◆Supervised Reward Inference9h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization9h◆Is Progressive Disclosure All You Need for Long-Context Agents?9h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability9h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification9h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration9h◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection9h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI9h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models9h◆Kernel Regression with Tensor Trains and Hadamard Overparameterization9h◆AI-Augmented Human Resource Management? Insights from German companies9h◆Diagnosing Correctness Probes under Self-Judgement Confounding9h◆BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025)9h◆America needs to stop getting shocked by Chinese AI2h◆Advancing next-gen AI with materials science innovation2h◆Gritt exits stealth with $34 million for robots to build solar plants—then, everything else3h◆Capacity and Redundancy Trade-offs in Multi-Task Learning9h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation9h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making9h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection9h◆Supervised Reward Inference9h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization9h◆Is Progressive Disclosure All You Need for Long-Context Agents?9h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability9h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification9h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration9h◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection9h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI9h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models9h◆Kernel Regression with Tensor Trains and Hadamard Overparameterization9h◆AI-Augmented Human Resource Management? Insights from German companies9h◆Diagnosing Correctness Probes under Self-Judgement Confounding9h◆BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025)9h◆
DataBubble·

Model Detail

thinkingmachines logo

Inkling-NVFP4

—
Provider: thinkingmachinesCategory: multimodalPipeline: image-text-to-text
DB Score
40.2
Downloads
66K
Likes
72
Day
+0.0%
Week
+0.0%
Month
+0.0%
Overview

Inkling-NVFP4 is a multimodal model with 276.4B parameters released by thinkingmachines. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.

Technical

Inkling-NVFP4 ships with 276.4B parameters. Total weight footprint is approximately 552.8 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

Use Cases

Inkling-NVFP4 is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.

Download History
Model Info
Licenseapache-2.0
Recent newsView all news →
Related News
techcrunchneutral5d ago

Thinking Machines amps up its bet against one-size-fits-all AI with its first open model, Inkling

It's the company's first public proof point after a year and a half spent building AI infrastructure largely out of public view.

huggingface6d ago

Welcome Inkling by Thinking Machines

arxiv70d ago

Hierarchical Multi-Fidelity Learning for Predicting Three-Dimensional Flame Wrinkling and Turbulent Burning Velocity

arXiv:2605.08232v1 Announce Type: new Abstract: High-fidelity experimental characterization of turbulent premixed flames remains limited by the cost and complexity of advanced diagnostics, particularly under elevated pressures and intense turbulence where measurements of coupled flame morphology and

Related Models
thinkingmachines logo
Inkling
thinkingmachines · 13K downloads
Qwen logo
Qwen3-VL-2B-Instruct
Qwen · 22.5M downloads
google logo
gemma-4-26B-A4B-it
Google · 13.2M downloads
HomeModelsNews